AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Towards Language-Guided Visual Recognition via Dynamic Convolutions

Gen Luo, Yiyi Zhou, Xiaoshuai Sun, Yongjian Wu, Yue Gao, Rongrong Ji

IJCV 2023 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 31 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
scale LaConvNet-S up to LaConvNet-B (10 to 19 blocks) (ablation)LaConvNet · RefCOCO val (REC)IoU@0.5 accuracy: 80.26 -> 82.46Improved
scale LaConvNet-S up to LaConvNet-B (ablation)LaConvNet · RefCOCO+ val (REC)IoU@0.5 accuracy: 69.82 -> 72.31Improved
scale LaConvNet-S up to LaConvNet-B (ablation)LaConvNet · RefCOCO+ val (RES)IoU: 57.16 -> 60.43Improved
scale LaConvNet-S up to LaConvNet-B (ablation)LaConvNet · CLEVR-Ref+IoU: 79.8 -> 82.3Improved
scale LaConvNet-S up to LaConvNet-B (ablation)LaConvNet · gRefCOCO valN-acc: 59.16 -> 58.06Hurt
replace TransVG (168M params) with LaConvNet-B (35M params)TransVG · RefCOCO+ val (REC)IoU@0.5 accuracy: 64.82 -> 72.31Improved
replace TransVG with LaConvNet-BTransVG · RefCOCO testB (REC)IoU@0.5 accuracy: 78.35 -> 78.16No clear effect
replace pre-trained VILLA-L with LaConvNet-BVILLA-L · RefCOCO+ val (REC)IoU@0.5 accuracy: 76.17 -> 72.31Hurt
replace IEP-Ref (with ground-truth programs) with LaConvNet-B, no program labelsIEP-Ref · CLEVR-Ref+IoU: 81.6 -> 82.3Improved
replace LAVT (Swin-T) with LaConvNet-BLAVT · RefCOCO+ val (RES)IoU: 57.02 -> 60.43Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy